CN110108431A - A kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm - Google Patents
A kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm Download PDFInfo
- Publication number
- CN110108431A CN110108431A CN201910427830.5A CN201910427830A CN110108431A CN 110108431 A CN110108431 A CN 110108431A CN 201910427830 A CN201910427830 A CN 201910427830A CN 110108431 A CN110108431 A CN 110108431A
- Authority
- CN
- China
- Prior art keywords
- signal
- vibration signal
- machine learning
- acceleration
- classification algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/021—Gearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M7/00—Vibration-testing of structures; Shock-testing of structures
- G01M7/02—Vibration-testing by means of a shake table
- G01M7/025—Measuring arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Acoustics & Sound (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
A kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm, comprising the following steps: step 1, using the vibration signal of acceleration transducer collection machinery equipment key point, and store vibration signal original waveform;Step 2, screening judgement is carried out to the vibration signal that step 1 collects;Step 3, the vibration signal after screening is pre-processed;Step 4, feature extraction is carried out to acceleration signal, speed signal obtained in step 3, envelope signal;Step 5, the resulting feature vector of step 4 is input in failure modes model, the corresponding fault diagnosis result of model output equipment.The present invention is based on the intelligent diagnostics models that machine learning classification algorithm establishes mechanical equipment, and then realize the intelligent diagnostics of mechanical equipment fault.
Description
Technical field
The invention belongs to mechanical fault diagnosis field, in particular to a kind of machinery based on machine learning classification algorithm
Equipment fault diagnosis method.
Background technique
With the horizontal fast lifting of the modernization of industry, mechanical equipment increasingly towards high speed, precise treatment, automation and is integrated
It is fast-developing to change direction.Rotary part in mechanical equipment, such as bearing, bearing shell, main shaft, gear-box, working environment are complicated more
Become, Chang Yinqi Work overload, changing load and is influenced to be easy to happen all kinds of failures by external extreme operating environments.If
Failure timely and effectively can not be diagnosed and be excluded, with failure deterioration and further development, will bring great security risk,
And cause heavy economic losses.
Traditional Trouble Diagnostic Method of Machinery Equipment is predominantly based on vibration signal processing and diagnose and based on failure machine
The diagnosis of reason.Both method for diagnosing faults are able to solve mechanism simply and the apparent mechanical equipment fault class of fault signature
Type.It is complicated for failure genesis mechanism, and signal spectrum is complicated, and fault signature discloses unconspicuous fault type, traditional
Method for diagnosing faults diagnosis effect is poor, accuracy is lower.
Summary of the invention
The purpose of the present invention is to provide a kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm, with
It solves the above problems.
To achieve the above object, the invention adopts the following technical scheme:
A kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm, comprising the following steps:
Step 1, using the vibration signal of acceleration transducer collection machinery equipment key point, and it is original to store vibration signal
Waveform;
Step 2, screening judgement is carried out to the vibration signal that step 1 collects, mechanical equipment shutdown status is deleted in cleaning
The vibration signal of lower acquisition;
Step 3, the vibration signal after screening is pre-processed;
Step 4, feature extraction is carried out to acceleration signal, speed signal obtained in step 3, envelope signal, feature mentions
It takes to extract including temporal signatures and be extracted with frequency domain character;
Step 5, the resulting feature vector of step 4 is input in failure modes model, the corresponding event of model output equipment
Hinder diagnostic result.
Further, in step 1, acceleration transducer need to guarantee that frequency response at least covers 1-10KHz, and have and be not less than
The sensitivity of 50mg/g;Mechanical equipment key point refers to mechanical equipment rotary shaft spring bearing position or mechanical equipment gear-box
The location of gear position or mechanical equipment other key components and parts.
Further, in step 2, screening judges the vibration signal of shutdown status firstly the need of calculating acceleration signal envelope
Peak value, by envelope peak compared with set shutdown threshold, if be less than or equal to shutdown threshold, acquired vibration signal pair
Answer equipment downtime state;Conversely, acquired vibration signal corresponds to equipment operation state;Wherein shutdown threshold is stopped by counting equipment
Acceleration envelope peak under machine state obtains.
Further, in step 3, pretreatment include primary integral is carried out to acceleration signal to obtain speed signal, and
The envelope for extracting acceleration signal, obtains the corresponding speed signal of acceleration signal and envelope signal with this.
Further, in step 4, the feature composition characteristic vector of extraction, the temporal signatures of extraction include virtual value, peak
Value, peak-to-peak value have dimension index and kurtosis, degree of skewness, peak index dimensionless index;The frequency domain character of extraction includes frequency band
Energy, frequency band energy accounting.
Further, in step 5, the building of failure modes model includes:
1) conclude, compile the vibration signal data and corresponding event of the fault case sample of same mechanical equipment type
Hinder label;
2) 1) vibration signal in is subjected to feature extraction, and composition characteristic vector, extracted feature vector and step one by one
Feature vector described in rapid four is consistent;
3) 2) all feature vectors in are divided, is divided into training set and test set, need to guarantees that training set is not less than
The 50% of total sample size, while dividing corresponding faulty tag in training set and test set and need to guarantee classification balance, quantity balance;
4) it selects machine learning classification algorithm to be trained training set, obtains failure modes model, test set is inputted
Whether the accuracy that category of model result is verified in failure modes model meets set provisioning request, if meeting the requirements, the failure
Disaggregated model is the model constructed;If not satisfied, then needing to carry out:
<1>tuning of sorting algorithm, comprising: screening, the adjustment of sorting algorithm inner parameter of sorting algorithm;
<2>screening of Modelling feature parameter;And be trained and test again, it is wanted until the nicety of grading of test set reaches
It asks.
Compared with prior art, the present invention has following technical effect:
The present invention is based on the intelligent diagnostics models that machine learning classification algorithm establishes mechanical equipment, and then realize mechanical equipment
The intelligent diagnostics of failure.Relative to traditional method for diagnosing faults, the present invention has automation, intelligent, diagnosis accuracy height
The advantages of.Intelligent diagnosing method of the invention simultaneously is able to solve the numerous mechanical equipments events of failure mechanism complexity, fault mode
Barrier diagnosis.Application through the invention is, it can be achieved that mechanical equipment fault precognition, provides decision-making foundation for machinery maintenance, have
Effect reduces equipment safety hidden danger, avoids heavy economic losses.
Detailed description of the invention
Fig. 1 is overall flow figure.
Fig. 2 is that operating status vibration signal screens logic chart.
Fig. 3 is vibration signal pretreatment process figure.
Fig. 4 is that vibration signal characteristics extract flow chart.
Fig. 5 is machine learning failure modes model construction flow chart.
Fig. 6 is fault case test set classification confusion matrix.
Specific embodiment
Below in conjunction with attached drawing, the present invention is further described:
Please refer to Fig. 1 to Fig. 6, a kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm, including with
Lower step:
Step 1, using the vibration signal of acceleration transducer collection machinery equipment key point, and it is original to store vibration signal
Waveform;
Step 2, screening judgement is carried out to the vibration signal that step 1 collects, mechanical equipment shutdown status is deleted in cleaning
The vibration signal of lower acquisition;
Step 3, the vibration signal after screening is pre-processed;
Step 4, feature extraction is carried out to acceleration signal, speed signal obtained in step 3, envelope signal, feature mentions
It takes to extract including temporal signatures and be extracted with frequency domain character;
Step 5, the resulting feature vector of step 4 is input in failure modes model, the corresponding event of model output equipment
Hinder diagnostic result.
In step 1, acceleration transducer need to guarantee that frequency response at least covers 1-10KHz, and have the spirit not less than 50mg/g
Sensitivity;Mechanical equipment key point refers to that mechanical equipment rotary shaft spring bearing position or mechanical equipment gear-box gear institute are in place
It sets or the location of mechanical equipment other key components and parts.
In step 2, screening judges that the vibration signal of shutdown status, will firstly the need of the peak value for calculating acceleration signal envelope
Envelope peak is compared with set shutdown threshold, if being less than or equal to shutdown threshold, acquired vibration signal corresponds to equipment and stops
Machine state;Conversely, acquired vibration signal corresponds to equipment operation state;Wherein shutdown threshold passes through under statistics equipment downtime state
Acceleration envelope peak obtain.
In step 3, pretreatment includes carrying out primary integral to acceleration signal to obtain speed signal, and extract acceleration
The envelope of signal obtains the corresponding speed signal of acceleration signal and envelope signal with this.
In step 4, the feature composition characteristic vector of extraction, the temporal signatures of extraction include that virtual value, peak value, peak-to-peak value have
Dimension index and kurtosis, degree of skewness, peak index dimensionless index;The frequency domain character of extraction includes frequency band energy, frequency band energy
Measure accounting.
In step 5, the building of failure modes model includes:
1) conclude, compile the vibration signal data and corresponding event of the fault case sample of same mechanical equipment type
Hinder label;
2) 1) vibration signal in is subjected to feature extraction, and composition characteristic vector, extracted feature vector and step one by one
Feature vector described in rapid four is consistent;
3) 2) all feature vectors in are divided, is divided into training set and test set, need to guarantees that training set is not less than
The 50% of total sample size, while dividing corresponding faulty tag in training set and test set and need to guarantee classification balance, quantity balance;
4) it selects machine learning classification algorithm to be trained training set, obtains failure modes model, test set is inputted
Whether the accuracy that category of model result is verified in failure modes model meets set provisioning request, if meeting the requirements, the failure
Disaggregated model is the model constructed;If not satisfied, then needing to carry out:
<1>tuning of sorting algorithm, comprising: screening, the adjustment of sorting algorithm inner parameter of sorting algorithm;
<2>screening of Modelling feature parameter;And be trained and test again, it is wanted until the nicety of grading of test set reaches
It asks.
Wherein:
Fig. 1 is overall flow figure, first with acceleration transducer collection machinery equipment vibrating signal, and to collected
Vibration signal carries out operating state signal screening judgement, is located in advance to the acceleration signal judged by operating status later
Reason, obtains corresponding speed signal and acceleration envelope signal, next extracts acceleration, three kinds of speed, acceleration envelope
The time domain and frequency domain character of signal, and its composition characteristic vector is input in failure modes model, finally by disaggregated model
The corresponding fault diagnosis result of output equipment.
Attached drawing 2 is that operating status vibration signal screens logic, carries out envelope to the acceleration signal collected first and mentions
It takes, calculates the peak value of acceleration envelope later, judge whether envelope peak is greater than the shutdown threshold of setting, if more than threshold is shut down
Value, then be the measuring signal under mechanical equipment operating status, signal retained;Conversely, for the survey under mechanical equipment shutdown status
Signal is measured, signal is deleted.
Attached drawing 3 is vibration signal pretreatment process, to the vibration acceleration for being judged to acquiring under mechanical equipment operating status
Signal carries out an integral operation and envelope extraction operation respectively, obtains speed signal and acceleration envelope signal.
Attached drawing 4 is that vibration signal characteristics extract process, to three kinds of speed, acceleration of acquisition, acceleration envelope class signals
Type carries out feature extraction respectively, extracts temporal signatures and frequency domain character, and by the combination of all characteristic parameters of extraction be characterized to
Amount.
Attached drawing 5 is machine learning failure modes model construction process, first to the event of certain mechanical equipment type of accumulation
Hinder casebook and carry out feature extraction, wherein fault case collection is by historical failure moment vibration signal collected and corresponding failure
Label composition.Secondly the feature vector of extraction is divided, the data volume for dividing 60% is training dataset, and residue 40% is
Test data set obtains disaggregated model in training concentration training using LightGBM machine learning classification algorithm, further according to classification
The parameter of classification accuracy adjustment sorting algorithm of the model on test set, while the screening of disaggregated model input parameter is carried out,
It finally obtains accuracy of classifying on test set and shows highest disaggregated model, using it as optimal failure modes model.
Attached drawing 6 is fault case test set classification confusion matrix, and horizontal axis is disaggregated model prediction result, and the longitudinal axis is test set
True fault label, the value in matrix indicate that forecast sample accounts for the ratio of true fault number of labels, cornerwise value table in figure
Show the accuracy of disaggregated model classification, as seen from the figure, the classification of the failure modes model on test set to all fault types
Accuracy is 90% or more.
Claims (6)
1. a kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm, which comprises the following steps:
Step 1, using the vibration signal of acceleration transducer collection machinery equipment key point, and the original wave of vibration signal is stored
Shape;
Step 2, screening judgement is carried out to the vibration signal that step 1 collects, cleaning is deleted and adopted under mechanical equipment shutdown status
The vibration signal of collection;
Step 3, the vibration signal after screening is pre-processed;
Step 4, feature extraction, feature extraction packet are carried out to acceleration signal, speed signal obtained in step 3, envelope signal
Temporal signatures are included to extract and frequency domain character extraction;
Step 5, the resulting feature vector of step 4 is input in failure modes model, the corresponding failure of model output equipment is examined
Disconnected result.
2. a kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm according to claim 1, special
Sign is, in step 1, acceleration transducer need to guarantee that frequency response at least covers 1-10KHz, and have sensitive not less than 50mg/g
Degree;Mechanical equipment key point refers to mechanical equipment rotary shaft spring bearing position or mechanical equipment gear-box gear position
Or the location of mechanical equipment other key components and parts.
3. a kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm according to claim 1, special
Sign is, in step 2, screening judges that the vibration signal of shutdown status, will firstly the need of the peak value for calculating acceleration signal envelope
Envelope peak is compared with set shutdown threshold, if being less than or equal to shutdown threshold, acquired vibration signal corresponds to equipment and stops
Machine state;Conversely, acquired vibration signal corresponds to equipment operation state;Wherein shutdown threshold passes through under statistics equipment downtime state
Acceleration envelope peak obtain.
4. a kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm according to claim 1, special
Sign is, in step 3, pretreatment includes carrying out primary integral to acceleration signal to obtain speed signal, and extract acceleration
The envelope of signal obtains the corresponding speed signal of acceleration signal and envelope signal with this.
5. a kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm according to claim 1, special
Sign is, in step 4, the feature composition characteristic vector of extraction, the temporal signatures of extraction include that virtual value, peak value, peak-to-peak value have
Dimension index and kurtosis, degree of skewness, peak index dimensionless index;The frequency domain character of extraction includes frequency band energy, frequency band energy
Measure accounting.
6. a kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm according to claim 1, special
Sign is, in step 5, the building of failure modes model includes:
1) conclude, compile same mechanical equipment type fault case sample vibration signal data and corresponding failure mark
Label;
2) 1) vibration signal in is subjected to feature extraction, and composition characteristic vector, extracted feature vector and step 4 one by one
The feature vector is consistent;
3) 2) all feature vectors in are divided, is divided into training set and test set, training set need to be guaranteed not less than gross sample
The 50% of this amount, at the same divide corresponding faulty tag in training set and test set need to guarantee classification balance, quantity balance;
4) it selects machine learning classification algorithm to be trained training set, failure modes model is obtained, by test set input fault
Whether the accuracy that category of model result is verified in disaggregated model meets set provisioning request, if meeting the requirements, the failure modes
Model is the model constructed;If not satisfied, then needing to carry out:
<1>tuning of sorting algorithm, comprising: screening, the adjustment of sorting algorithm inner parameter of sorting algorithm;
<2>screening of Modelling feature parameter;And be trained and test again, until the nicety of grading of test set reaches requirement.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910427830.5A CN110108431B (en) | 2019-05-22 | 2019-05-22 | Mechanical equipment fault diagnosis method based on machine learning classification algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910427830.5A CN110108431B (en) | 2019-05-22 | 2019-05-22 | Mechanical equipment fault diagnosis method based on machine learning classification algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110108431A true CN110108431A (en) | 2019-08-09 |
CN110108431B CN110108431B (en) | 2021-07-16 |
Family
ID=67491611
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910427830.5A Active CN110108431B (en) | 2019-05-22 | 2019-05-22 | Mechanical equipment fault diagnosis method based on machine learning classification algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110108431B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110595811A (en) * | 2019-09-11 | 2019-12-20 | 浙江工业大学之江学院 | Method for constructing health state characteristic diagram of mechanical equipment |
CN110594107A (en) * | 2019-10-24 | 2019-12-20 | 内蒙古青电云电力服务有限公司 | Wind turbine generator fault detection method and device based on rapid gradient elevator |
CN110816589A (en) * | 2019-10-31 | 2020-02-21 | 北京英诺威尔科技股份有限公司 | CTCS3 fault diagnosis method based on machine learning |
CN111397896A (en) * | 2020-03-08 | 2020-07-10 | 华中科技大学 | Fault diagnosis method and system for rotary machine and storage medium |
CN111930081A (en) * | 2020-07-15 | 2020-11-13 | 西门子工厂自动化工程有限公司 | Method and device for monitoring AGV state, edge device and storage medium |
CN111950442A (en) * | 2020-08-10 | 2020-11-17 | 江苏聚力智能机械股份有限公司 | Stereo garage motor fault diagnosis method using DBN multi-domain feature extraction |
CN112380932A (en) * | 2020-11-02 | 2021-02-19 | 上海三菱电梯有限公司 | Vibration signal characteristic value selection method and elevator health state evaluation or fault diagnosis method |
CN112525334A (en) * | 2020-11-18 | 2021-03-19 | 西安因联信息科技有限公司 | Dynamic equipment vibration multistable detection method |
CN112580252A (en) * | 2020-11-26 | 2021-03-30 | 北京航天智造科技发展有限公司 | Rotor drop-out fault diagnosis and analysis method and device |
CN112613157A (en) * | 2020-11-26 | 2021-04-06 | 北京航天智造科技发展有限公司 | Rotor fault analysis method and device |
CN112729815A (en) * | 2020-12-21 | 2021-04-30 | 云南迦南飞奇科技有限公司 | Wireless network-based online fault big data early warning method for health condition of transmission line |
CN113392936A (en) * | 2021-07-09 | 2021-09-14 | 四川英创力电子科技股份有限公司 | Oven fault diagnosis method based on machine learning |
CN113551927A (en) * | 2021-07-07 | 2021-10-26 | 广州赛意信息科技股份有限公司 | Mechanical equipment fault early warning method and system based on vibration signals |
TWI758824B (en) * | 2020-08-18 | 2022-03-21 | 神通資訊科技股份有限公司 | Abnormality detection and breakage detection system for mechanical operation and the method thereof |
WO2022062161A1 (en) * | 2020-09-28 | 2022-03-31 | 广东石油化工学院 | Large machine set friction fault analysis method and system based on waveform and dimensionless learning |
WO2022174441A1 (en) * | 2021-02-22 | 2022-08-25 | 罗伯特·博世有限公司 | Method and apparatus for monitoring health state of mechanical apparatus or mechanical component |
CN117609692A (en) * | 2023-11-14 | 2024-02-27 | 中节能风力发电股份有限公司 | Method and device for diagnosing parallel level faults of gear boxes of wind generating set |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101122583A (en) * | 2007-09-06 | 2008-02-13 | 华中科技大学 | Sheared frame structure damage detection method |
CN101281117A (en) * | 2008-05-29 | 2008-10-08 | 上海交通大学 | Wide span rail traffic bridge damnification recognition method |
CN104502103A (en) * | 2014-12-07 | 2015-04-08 | 北京工业大学 | Bearing fault diagnosis method based on fuzzy support vector machine |
CN107271170A (en) * | 2017-07-12 | 2017-10-20 | 西安因联信息科技有限公司 | The automatic diagnosis method and system of a kind of mechanical equipment fault type |
CN108388860A (en) * | 2018-02-12 | 2018-08-10 | 大连理工大学 | A kind of Aeroengine Ball Bearings method for diagnosing faults based on power entropy-spectrum-random forest |
CN108414226A (en) * | 2017-12-25 | 2018-08-17 | 哈尔滨理工大学 | Fault Diagnosis of Roller Bearings under the variable working condition of feature based transfer learning |
CN108731923A (en) * | 2018-03-28 | 2018-11-02 | 中控技术(西安)有限公司 | A kind of fault detection method and device of rotating machinery |
CN109145706A (en) * | 2018-06-19 | 2019-01-04 | 徐州医科大学 | A kind of sensitive features selection and dimension reduction method for analysis of vibration signal |
-
2019
- 2019-05-22 CN CN201910427830.5A patent/CN110108431B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101122583A (en) * | 2007-09-06 | 2008-02-13 | 华中科技大学 | Sheared frame structure damage detection method |
CN101281117A (en) * | 2008-05-29 | 2008-10-08 | 上海交通大学 | Wide span rail traffic bridge damnification recognition method |
CN104502103A (en) * | 2014-12-07 | 2015-04-08 | 北京工业大学 | Bearing fault diagnosis method based on fuzzy support vector machine |
CN107271170A (en) * | 2017-07-12 | 2017-10-20 | 西安因联信息科技有限公司 | The automatic diagnosis method and system of a kind of mechanical equipment fault type |
CN108414226A (en) * | 2017-12-25 | 2018-08-17 | 哈尔滨理工大学 | Fault Diagnosis of Roller Bearings under the variable working condition of feature based transfer learning |
CN108388860A (en) * | 2018-02-12 | 2018-08-10 | 大连理工大学 | A kind of Aeroengine Ball Bearings method for diagnosing faults based on power entropy-spectrum-random forest |
CN108731923A (en) * | 2018-03-28 | 2018-11-02 | 中控技术(西安)有限公司 | A kind of fault detection method and device of rotating machinery |
CN109145706A (en) * | 2018-06-19 | 2019-01-04 | 徐州医科大学 | A kind of sensitive features selection and dimension reduction method for analysis of vibration signal |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110595811A (en) * | 2019-09-11 | 2019-12-20 | 浙江工业大学之江学院 | Method for constructing health state characteristic diagram of mechanical equipment |
CN110594107A (en) * | 2019-10-24 | 2019-12-20 | 内蒙古青电云电力服务有限公司 | Wind turbine generator fault detection method and device based on rapid gradient elevator |
CN110816589A (en) * | 2019-10-31 | 2020-02-21 | 北京英诺威尔科技股份有限公司 | CTCS3 fault diagnosis method based on machine learning |
CN111397896A (en) * | 2020-03-08 | 2020-07-10 | 华中科技大学 | Fault diagnosis method and system for rotary machine and storage medium |
CN111930081A (en) * | 2020-07-15 | 2020-11-13 | 西门子工厂自动化工程有限公司 | Method and device for monitoring AGV state, edge device and storage medium |
CN111950442A (en) * | 2020-08-10 | 2020-11-17 | 江苏聚力智能机械股份有限公司 | Stereo garage motor fault diagnosis method using DBN multi-domain feature extraction |
TWI758824B (en) * | 2020-08-18 | 2022-03-21 | 神通資訊科技股份有限公司 | Abnormality detection and breakage detection system for mechanical operation and the method thereof |
WO2022062161A1 (en) * | 2020-09-28 | 2022-03-31 | 广东石油化工学院 | Large machine set friction fault analysis method and system based on waveform and dimensionless learning |
CN112380932A (en) * | 2020-11-02 | 2021-02-19 | 上海三菱电梯有限公司 | Vibration signal characteristic value selection method and elevator health state evaluation or fault diagnosis method |
CN112525334A (en) * | 2020-11-18 | 2021-03-19 | 西安因联信息科技有限公司 | Dynamic equipment vibration multistable detection method |
CN112580252A (en) * | 2020-11-26 | 2021-03-30 | 北京航天智造科技发展有限公司 | Rotor drop-out fault diagnosis and analysis method and device |
CN112613157A (en) * | 2020-11-26 | 2021-04-06 | 北京航天智造科技发展有限公司 | Rotor fault analysis method and device |
CN112729815A (en) * | 2020-12-21 | 2021-04-30 | 云南迦南飞奇科技有限公司 | Wireless network-based online fault big data early warning method for health condition of transmission line |
WO2022174441A1 (en) * | 2021-02-22 | 2022-08-25 | 罗伯特·博世有限公司 | Method and apparatus for monitoring health state of mechanical apparatus or mechanical component |
CN113551927A (en) * | 2021-07-07 | 2021-10-26 | 广州赛意信息科技股份有限公司 | Mechanical equipment fault early warning method and system based on vibration signals |
CN113392936A (en) * | 2021-07-09 | 2021-09-14 | 四川英创力电子科技股份有限公司 | Oven fault diagnosis method based on machine learning |
CN117609692A (en) * | 2023-11-14 | 2024-02-27 | 中节能风力发电股份有限公司 | Method and device for diagnosing parallel level faults of gear boxes of wind generating set |
CN117609692B (en) * | 2023-11-14 | 2024-04-30 | 中节能风力发电股份有限公司 | Method and device for diagnosing parallel level faults of gear boxes of wind generating set |
Also Published As
Publication number | Publication date |
---|---|
CN110108431B (en) | 2021-07-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110108431A (en) | A kind of Trouble Diagnostic Method of Machinery Equipment based on machine learning classification algorithm | |
CN102192825B (en) | User interface system and method for diagnosing a rotating machine condition not based upon prior measurement history | |
CN110006645B (en) | Multi-source fusion high-voltage circuit breaker mechanical fault diagnosis method | |
CN110376522B (en) | Motor fault diagnosis method of data fusion deep learning network | |
CN112200032B (en) | Online monitoring method for mechanical state of high-voltage circuit breaker based on attention mechanism | |
CN111537173B (en) | Digital twinning-based microelectronic product drop impact reliability assessment method | |
CN107461342A (en) | A kind of centrifugal pump fault inline diagnosis method and system | |
CN111504675B (en) | On-line diagnosis method for mechanical fault of gas insulated switchgear | |
CN107545349A (en) | A kind of Data Quality Analysis evaluation model towards electric power big data | |
CN111946559B (en) | Method for detecting structures of wind turbine foundation and tower | |
CN108204895A (en) | A kind of Wind turbines change gear box fault diagnosis method and system | |
CN101533052B (en) | Testing system and method for PWM fan electrical performance | |
CN110069411A (en) | Client performance quality report generation method, device, medium and electronic equipment | |
CN101726414A (en) | Method and system thereof for measuring trial run parameter of aeroengine | |
CN105786678A (en) | Relevance model-based testability prediction method | |
CN103234742B (en) | Fault diagnosis method for damping springs of vibrating screen | |
CN106203637A (en) | A kind of mobile system health evaluating method based on mahalanobis distance and health index | |
US11867763B2 (en) | Method for monitoring circuit breaker and apparatus and internet of things using the same | |
CN111896254A (en) | Fault prediction system and method for variable-speed variable-load large rolling bearing | |
CN106932200A (en) | The Gaussian process multiple features intelligent diagnosing method of rolling bearing fault | |
CN111627199A (en) | Hydropower station dam safety monitoring system and monitoring method | |
CN102608519B (en) | Circuit failure diagnosis method based on node information | |
CN109376778A (en) | A kind of failure modes diagnostic method based on characteristic variable weighting | |
CN115238785A (en) | Rotary machine fault diagnosis method and system based on image fusion and integrated network | |
CN107607342A (en) | The healthy efficiency detection method of Air Conditioning Facilities device cluster |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |